Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/codacy/codacy-skillsnpx agentmods add skills/codacy/codacy-skills/codacy-code-reviewWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/codacy/codacy-skills/codacy-code-review)<a href="https://agentmods.dev/skills/codacy/codacy-skills/codacy-code-review"><img src="https://agentmods.dev/badge/skills/codacy/codacy-skills/codacy-code-review/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/codacy/codacy-skills/codacy-code-review"><img src="https://agentmods.dev/badge/skills/codacy/codacy-skills/codacy-code-review.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
SkillSpector: 1 finding, up to low
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- low Excessive Agency · line 147 Skill's behavior or capabilities extend beyond its stated purpose. Scope creep allows an agent to perform actions unrelated to its documented functionality, increasing the attack surface.Fix: Limit the skill's scope to its documented purpose. Remove instructions that enable the agent to perform actions outside its stated functionality.
What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00117 | $0.02223 |
| Opus 5.5 | $0.00047 | $0.00889 |
| Sonnet 5.5 | $0.00023 | $0.00445 |
| Haiku 4.5 | $0.00012 | $0.00222 |
Grade A, and why
codacy-code-review scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 1mo ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
Copies of this mod
1 near-identical copy found in the catalogue:
- codacy-code-review — 88% identical, 1 lines differ
How it starts
The opening of the file, as written. The whole thing — 197 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Codacy Code Review
Glossary: See glossary.md for shared definitions of Codacy concepts (issues, findings, severity, coverage, tools, patterns, etc.).
This skill enriches code reviews with Codacy data. It works alongside any existing code review process (a code-review skill, CodeRabbit, manual review, etc.) — it adds Codacy-specific data on top.
Prerequisites
- Codacy Analysis CLI (
codacy-analysis) — for fast local analysis. Seecodacy-analysis-clifor setup. - Codacy Cloud CLI (
codacy) — for coverage data, quality gate status, and ignoring issues. Seecodacy-cloud-clifor setup.
Both CLIs share credentials at ~/.codacy/credentials, so a single login covers both.
Local vs Cloud analysis
This skill uses two complementary analysis sources:
| Source | What it provides | Speed |
|---|---|---|
| Analysis CLI (local) | Issues and security findings on PR changes | Instant — no push or remote analysis needed |
| Cloud CLI (remote) | Coverage delta, quality gate, duplication, issue management (ignore/unignore) | Requires the PR to be pushed and analyzed by Codacy |
Prefer local analysis for issue detection — it runs immediately on the current working tree with --pr and doesn't require waiting for remote analysis. Use the Cloud CLI to supplement with coverage data and quality gate status, and to manage issues (ignore/unignore).
The Analysis CLI may not support every tool that Codacy Cloud runs. If the project uses tools not available locally (check with codacy-analysis analyze --inspect --output-format json), flag that some findings may only appear in the Cloud results.
How Codacy PR data works
- Cloud data reflects the HEAD commit of the PR — the remote analysis shown is always for the latest push to the PR branch, not a specific commit.
- Local analysis reflects the working tree —
codacy-analysis analyze --prcompares the current branch against the PR's target branch, catching issues even before pushing. - Ignoring issues is a Cloud-only operation — it takes effect immediately on Codacy but any other configuration changes (patterns, tools) only apply after the next remote analysis.
- Stale or missing remote analysis — if the Cloud PR analysis appears outdated or incomplete, use
codacy pull-request <provider> <org> <repo> <prNumber> --reanalyze-and-waitto trigger reanalysis and block until it completes (polls every 10 seconds, up to 20 minutes). For fire-and-forget, use--reanalyzeinstead and re-check manually. - Auto-detection — when running inside the repo, the Cloud CLI auto-detects provider/org/repo from the git remote. Commands like
codacy pull-request <prNumber>work without explicit parameters.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 1mo ago Changed · +6 lines 3c35c6a0df74
- 1mo ago First seen · 191 lines · 117 tokens per session scan A 0c0d8e0d756d
codacy-code-review is a skill published in the GitHub repository codacy/codacy-skills (14 stars, last pushed 1mo ago), licensed MIT. It adds 117 tokens to every session and 2,223 once invoked, about $0.0005 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
autoreview
Structured code review through the shared OpenClaw agent-skills installation.
omh-code-review
This is an OMH code-review workflow skill, projected for Agent Skills hosts (Claude Code, Codex, Cursor, opencode, OpenClaw, pi).
revdiff-plan
Review the last Codex assistant message (plan, analysis, or proposal) with inline annotations in a TUI overlay. Extracts the most recent response from Codex rollout files and opens it in revdiff for review and annotation. Activates on "revdiff-plan", "review plan with revdiff", "annotate plan", "review last response"…
re0-merge
Review and land an external contribution the way this suite does: gate it against the thesis, land it with the author's credit intact, complete a new skill rather than merging it raw, then approve, credit, and explain before closing. Use when reviewing a pull request, as any collaborator or maintainer, not only the…
explore-unknowns
Guide the user through a quadrant walk that maps the unknowns of a task — open by listing the known knowns, then work through known unknowns, unknown knowns, and unknown unknowns one stage at a time, ending with a complete four-quadrant map in the user's hands. Use when a request is ambiguous or underspecified, the…
asplos-writing-style
Use when drafting or revising ASPLOS prose — engineering the first two pages that rapid review actually reads, stating the cross-layer insight as one quotable sentence, structuring per-layer mechanism sections, writing bounded claims, and fitting everything into 11 self-contained pages that include figures and…